This poster is published under an
open license. Please read the
disclaimer for further details.
Keywords:
Image verification, Image registration, Cancer, Screening, Computer Applications-General, Ultrasound, Computer applications, Breast
Authors:
S. S. Andrei1, J. Gao1, J. Chiu2, J. Turian3, C. Caluser4; 1Villa Park, IL/US, 2Evanston, IL/US, 3Chicago, IL/US, 4Glen Ellyn, IL/US
DOI:
10.1594/ecr2014/C-1382
Aims and objectives
In addition to mammography,
ultrasound imaging has become an important tool in the fight against breast cancer,
a disease which in 2011 took an estimated 39,520 lives and added 288,130 new cases,
in the US alone [1].
Breast ultrasound has been a proven tool for early breast cancer detection,
however it has been hindered by its results quality significant dependency on the operator's skill,
among other limitations [2]. It is inherently difficult to assess the completeness of freehand breast ultrasound scans [3] in order to avoid missing small cancers.
This task is further complicated by the anatomic and physiological factors,
especially body habitus,
patient motion and breast tissue deformation during the exam.
The positional tracking of the entire breast volume,
during the handheld ultrasound examination,
is therefore a difficult task in terms of: technology,
methodology and expertise. The capability of a newly developed automated freehand ultrasound mapping system (FHUMS),
to alleviate some of the limitations mentioned above,
was evaluated.
In this work we report the laboratory results obtained with the FHUMS in conditions simulating clinical handheld breast ultrasound exams.
The FHUMS generated surface breast contour (SBC) and the scanned breast surface area map (SAM) integrity,
accuracy and precision are tested and reported in this study.